# Invertible Convolution with Symmetric Paddings

arXiv: https://arxiv.org/abs/2303.17361 · HTML: https://mlsanity.com/paper/2303.17361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 7 of 7)

- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [Invertible Residual Networks](https://mlsanity.com/paper/1811.00995/) (2018)
- [Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models](https://mlsanity.com/paper/2002.07101/) (2020)
- [Densely connected normalizing flows](https://mlsanity.com/paper/2106.04627/) (2021)
- [VFlow: More Expressive Generative Flows with Variational Data Augmentation](https://mlsanity.com/paper/2002.09741/) (2020)
- [MaCow: Masked Convolutional Generative Flow](https://mlsanity.com/paper/1902.04208/) (2019)
- [Emerging Convolutions for Generative Normalizing Flows](https://mlsanity.com/paper/1901.11137/) (2019)

## Abstract (arXiv)

We show that symmetrically padded convolution can be analytically inverted via DFT. We comprehensively analyze several different symmetric and anti-symmetric padding modes and show that multiple cases exist where the inversion can be achieved. The implementation is available at urlhttps://github.com/prclibo/iconvdft.